Dynamic modelling and control of membrane filtration process

Abstract

Membrane filtration process is promising technology in separation process. However, this technology involves many interactions from biological and physical operation behaviour. Membrane fouling in filtration process is another complex problem that needs to be understood to ensure efficient filtration process. The aim of this paper is to study the potential of neural network based dynamic model for submerged membrane filtration process. The purpose of the model is to represent the dynamic behaviour of the filtration process therefore suitable control strategy and tuning of the controller can be developed to control the filtration process more effectively. In this work, a feed-forward neural network (FFNN) and radial basis function neural network (RBFNN) were employed with dynamic structure to develop the model of the filtration process. The random step was applied to the suction pump to obtained the permeate flux and transmembrane pressure (TMP) dynamic. The model was evaluated in term of %R2, root mean square error (RMSE,) and mean absolute deviation (MAD). The result of proposed modelling technique showed that the RNN structure is able to model the dynamic behaviour of the filtration process. The developed model also can be a reliable aid for the control strategy development in the membrane filtration process.